© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5200
    Prev
    Next
    INDEX
    Explanations

    a mix of words and phrases from code snippets, technical documentation, and German text related to grammar and sentence structure.

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    einer
    -0.64
     einer
    -0.56
     Potts
    -0.53
     kobiety
    -0.52
     osoby
    -0.51
     spotkania
    -0.51
     badania
    -0.50
    einem
    -0.50
     ženy
    -0.49
     ně
    -0.49
    POSITIVE LOGITS
     den
    0.75
    脚注の使い方
    0.64
    saraba
    0.63
     Pristupljeno
    0.61
    oredCriteria
    0.60
     cherchés
    0.60
    NameInMap
    0.58
    bewerken
    0.57
     diesen
    0.56
     okuyayım
    0.56
    Activations Density 0.718%

    No Known Activations